Releasesby GlyphNova-3 Model Update
🌏 Nova-3 now supports the following new languages and language codes: Chinese (Mandarin, Simplified): zh , zh-CN , zh-Hans Chinese (Mandarin, Traditional): zh-TW , zh-Hant Access these models by setting model="nova-3" and the relevant language code in your request. Learn more about Nova-3 and supported languages on the Models and Language Overview page.
Also shipped Mar 31, 2026Deepgram in March 2026 →
DNS - Internal DNS - now in open beta
Internal DNS is now in open beta. Who can use it? Internal DNS is bundled as a part of Cloudflare Gateway and is now available to every Enterprise customer with one of the following subscriptions: Cloudflare Zero Trust Enterprise Cloudflare Gateway Enterprise To learn more and get started, refer to the Internal DNS documentation .
New Sampling Parameters The following parameters are now available on all models: - frequency_penalty –...
New Sampling Parameters The following parameters are now available on all models: frequency_penalty – Reduces repetition by penalizing tokens based on how often they have appeared so far presence_penalty – Reduces repetition by penalizing tokens that have appeared at least once logit_bias – Adjusts the likelihood of specific tokens appearing in the response
Netlify CLI adds prompt-based creation and anonymous deploys
We've improved the Netlify CLI's Agent Experience to make it the fastest way for both developers and AI agents to go from idea to deployed site. Here's what's new. Create a new project from a prompt The netlify create command now builds you a new site from scratch, triggering Agent Runners: netlify create "a landing page for a SaaS product with a waitlist...
Alertmanager status endpoint requires a new permission
The GET /api/alertmanager/grafana/api/v2/status endpoint previously required the legacy alert.notifications:read permission. It now requires a dedicated alert.notifications.system-status:read permission. This new permission is included in the fixed:alerting.notifications:writer role, which is granted to Admin users by default.
unstructured 0.22.10
- fix(chunking): preserve nested table structure in reconstruction - Replace lazyproperty with functools.cached_property - mem: reduce PaddleOCR rec_batch_num from 6 to 1 - fix: isolate Table elements in pre-chunks - feat(chunking): repeat table headers on continuation chunks
Advanced Channel Classifier Template
Description: Amplitude’s enhanced out-of-the-box channel classifiers automatically group traffic from sources and referrers like Paid and Organic Search, Email, Affiliates, LLM channels, and more. Why: Your dashboards and Global Agent clearly show trends and impact from every channel investment without any added analytics set-up.
More from DeepgramEvery Deepgram release →
New thought_signature field for Gemini function calling
The Voice Agent API now includes an optional thought_signature field in function call messages. Some Gemini models (3.0 and 3.1 families) require this as an additional function call identifier.
Example
{ "type": "FunctionCallRequest", "functions": [ { "id": "fc_12345678-90ab-cdef-1234-567890abcdef", "name": "get_weather", "arguments": "{\"location\": \"Fremont, CA 94539\"}", "client_side": true, "thought_signature": "abc123" } ] } The thought_signature field is optional and only relevant when using Google Gemini models.
New volume parameter for Cartesia TTS
The Voice Agent API now supports an optional agent.speak.provider.volume parameter when using Cartesia as the TTS provider. Valid values range from 0.5 to 2.0 . For more details, see Configure the Voice Agent or the Cartesia volume, speed, and emotion documentation .
Container Images (release 260402)
- quay.io/deepgram/self-hosted-api:release-260402 Equivalent image to: quay.io/deepgram/self-hosted-api:1.181.3 quay.io/deepgram/self-hosted-engine:release-260402 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.114.5 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260402 Equivalent image to...
This Release Contains The Following Changes
- Certificate Endpoint Fix , Engine now responds to /v1/certificates in addition to /certificates , consistent with the other container images. See Certificate Status for details. Model Name Consistency , The /v1/models endpoint now returns a canonical_name field matching the model name used in /v1/listen requests.
NVIDIA LLM provider now available
NVIDIA is now a supported LLM provider for the Voice Agent API. The following model is available in the Standard pricing tier: nemotron-3-nano-30B-A3B , Nemotron 3 Nano 30B A3B provides cost efficiency with high accuracy for targeted agentic tasks.
TTS speak speed (Early Access)
You can now control the speaking rate of Deepgram TTS in the Voice Agent API using the agent.speak.provider.speed parameter. This parameter accepts a float value between 0.7 and 1.5 , with 1.0 as the default.
Updated LLM models
New OpenAI models , Two new models are now available in the Standard pricing tier: gpt-5.4-nano gpt-5.4-mini Gemini 2.0 Flash deprecated , The gemini-2.0-flash model is now deprecated. We recommend migrating to gemini-2.5-flash or a newer Gemini model. See the Google models table for alternatives.